RPCSX/llvm
1
0
Fork 0
mirror of https://github.com/RPCSX/llvm.git synced 2024-12-13 23:18:51 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity
970d6e800d
llvm/test/CodeGen/AMDGPU/trunc.ll

101 lines
3.6 KiB
LLVM
Raw Normal View History

AMDGPU: Support commuting with immediate in src0 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@280970 91177308-0d34-0410-b5e6-96231b3b80d8
2016-09-08 17:19:29 +00:00
; RUN: llc -march=amdgcn -verify-machineinstrs< %s | FileCheck -check-prefix=SI %s
R600: Fix i64 to i32 trunc on SI git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190091 91177308-0d34-0410-b5e6-96231b3b80d8
2013-09-05 19:41:10 +00:00
; RUN: llc -march=r600 -mcpu=cypress < %s | FileCheck -check-prefix=EG %s
R600/SI: Fix i64 truncate to i1 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@228273 91177308-0d34-0410-b5e6-96231b3b80d8
2015-02-05 06:05:13 +00:00
declare i32 @llvm.r600.read.tidig.x() nounwind readnone
R600: Fix i64 to i32 trunc on SI git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190091 91177308-0d34-0410-b5e6-96231b3b80d8
2013-09-05 19:41:10 +00:00
define void @trunc_i64_to_i32_store(i32 addrspace(1)* %out, i64 %in) {
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218776 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-01 17:15:17 +00:00
; SI-LABEL: {{^}}trunc_i64_to_i32_store:
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" MATCHES=`grep -v Patterns SIInstructions.td | grep -o '"[A-Z0-9_]\+["e]' | grep -o '[A-Z0-9_]\+' | sort -r` for f in $TEST_FILES; do # Check that there are SI tests: grep -q -e 'verde' -e 'bonaire' -e 'SI' -e 'tahiti' $f if [ $? -eq 0 ]; then for match in $MATCHES; do sed -i -e "s/\([ :]$match\)/\L\1/" $f done # Try to get check lines with partial instruction names sed -i 's/\(;[ ]*SI[A-Z\\-]*: \)\([A-Z_0-9]\+\)/\1\L\2/' $f fi done sed -i -e 's/bb0_1/BB0_1/g' ../../../test/CodeGen/R600/infinite-loop.ll sed -i -e 's/SI-NOT: bfe/SI-NOT: {{[^@]}}bfe/g'../../../test/CodeGen/R600/llvm.AMDGPU.bfe.*32.ll ../../../test/CodeGen/R600/sext-in-reg.ll sed -i -e 's/exp_IEEE/EXP_IEEE/g' ../../../test/CodeGen/R600/llvm.exp2.ll sed -i -e 's/numVgprs/NumVgprs/g' ../../../test/CodeGen/R600/register-count-comments.ll sed -i 's/\(; CHECK[-NOT]*: \)\([A-Z_0-9]\+\)/\1\L\2/' ../../../test/CodeGen/R600/select64.ll ../../../test/CodeGen/R600/sgpr-copy.ll //==================================================================// // Shell script for converting .td files (run this last) //==================================================================// export LC_ALL='C' sed -i -e '/Patterns/!s/\("[A-Z0-9_]\+[ "e]\)/\L\1/g' SIInstructions.td sed -i -e 's/"EXP/"exp/g' SIInstrInfo.td git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@221350 91177308-0d34-0410-b5e6-96231b3b80d8
2014-11-05 14:50:53 +00:00
; SI: s_load_dword [[SLOAD:s[0-9]+]], s[0:1], 0xb
; SI: v_mov_b32_e32 [[VLOAD:v[0-9]+]], [[SLOAD]]
; SI: buffer_store_dword [[VLOAD]]
R600: Fix i64 to i32 trunc on SI git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190091 91177308-0d34-0410-b5e6-96231b3b80d8
2013-09-05 19:41:10 +00:00
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218776 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-01 17:15:17 +00:00
; EG-LABEL: {{^}}trunc_i64_to_i32_store:
R600: Fix i64 to i32 trunc on SI git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190091 91177308-0d34-0410-b5e6-96231b3b80d8
2013-09-05 19:41:10 +00:00
; EG: MEM_RAT_CACHELESS STORE_RAW T0.X, T1.X, 1
; EG: LSHR
; EG-NEXT: 2(
%result = trunc i64 %in to i32 store i32 %result, i32 addrspace(1)* %out, align 4
ret void
}
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218776 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-01 17:15:17 +00:00
; SI-LABEL: {{^}}trunc_load_shl_i64:
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" MATCHES=`grep -v Patterns SIInstructions.td | grep -o '"[A-Z0-9_]\+["e]' | grep -o '[A-Z0-9_]\+' | sort -r` for f in $TEST_FILES; do # Check that there are SI tests: grep -q -e 'verde' -e 'bonaire' -e 'SI' -e 'tahiti' $f if [ $? -eq 0 ]; then for match in $MATCHES; do sed -i -e "s/\([ :]$match\)/\L\1/" $f done # Try to get check lines with partial instruction names sed -i 's/\(;[ ]*SI[A-Z\\-]*: \)\([A-Z_0-9]\+\)/\1\L\2/' $f fi done sed -i -e 's/bb0_1/BB0_1/g' ../../../test/CodeGen/R600/infinite-loop.ll sed -i -e 's/SI-NOT: bfe/SI-NOT: {{[^@]}}bfe/g'../../../test/CodeGen/R600/llvm.AMDGPU.bfe.*32.ll ../../../test/CodeGen/R600/sext-in-reg.ll sed -i -e 's/exp_IEEE/EXP_IEEE/g' ../../../test/CodeGen/R600/llvm.exp2.ll sed -i -e 's/numVgprs/NumVgprs/g' ../../../test/CodeGen/R600/register-count-comments.ll sed -i 's/\(; CHECK[-NOT]*: \)\([A-Z_0-9]\+\)/\1\L\2/' ../../../test/CodeGen/R600/select64.ll ../../../test/CodeGen/R600/sgpr-copy.ll //==================================================================// // Shell script for converting .td files (run this last) //==================================================================// export LC_ALL='C' sed -i -e '/Patterns/!s/\("[A-Z0-9_]\+[ "e]\)/\L\1/g' SIInstructions.td sed -i -e 's/"EXP/"exp/g' SIInstrInfo.td git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@221350 91177308-0d34-0410-b5e6-96231b3b80d8
2014-11-05 14:50:53 +00:00
; SI-DAG: s_load_dwordx2
; SI-DAG: s_load_dword [[SREG:s[0-9]+]],
; SI: s_lshl_b32 [[SHL:s[0-9]+]], [[SREG]], 2
; SI: v_mov_b32_e32 [[VSHL:v[0-9]+]], [[SHL]]
; SI: buffer_store_dword [[VSHL]],
R600: Implement isNarrowingProfitable. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@204658 91177308-0d34-0410-b5e6-96231b3b80d8
2014-03-24 19:43:31 +00:00
define void @trunc_load_shl_i64(i32 addrspace(1)* %out, i64 %a) {
%b = shl i64 %a, 2
%result = trunc i64 %b to i32
store i32 %result, i32 addrspace(1)* %out, align 4
ret void
}
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218776 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-01 17:15:17 +00:00
; SI-LABEL: {{^}}trunc_shl_i64:
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" MATCHES=`grep -v Patterns SIInstructions.td | grep -o '"[A-Z0-9_]\+["e]' | grep -o '[A-Z0-9_]\+' | sort -r` for f in $TEST_FILES; do # Check that there are SI tests: grep -q -e 'verde' -e 'bonaire' -e 'SI' -e 'tahiti' $f if [ $? -eq 0 ]; then for match in $MATCHES; do sed -i -e "s/\([ :]$match\)/\L\1/" $f done # Try to get check lines with partial instruction names sed -i 's/\(;[ ]*SI[A-Z\\-]*: \)\([A-Z_0-9]\+\)/\1\L\2/' $f fi done sed -i -e 's/bb0_1/BB0_1/g' ../../../test/CodeGen/R600/infinite-loop.ll sed -i -e 's/SI-NOT: bfe/SI-NOT: {{[^@]}}bfe/g'../../../test/CodeGen/R600/llvm.AMDGPU.bfe.*32.ll ../../../test/CodeGen/R600/sext-in-reg.ll sed -i -e 's/exp_IEEE/EXP_IEEE/g' ../../../test/CodeGen/R600/llvm.exp2.ll sed -i -e 's/numVgprs/NumVgprs/g' ../../../test/CodeGen/R600/register-count-comments.ll sed -i 's/\(; CHECK[-NOT]*: \)\([A-Z_0-9]\+\)/\1\L\2/' ../../../test/CodeGen/R600/select64.ll ../../../test/CodeGen/R600/sgpr-copy.ll //==================================================================// // Shell script for converting .td files (run this last) //==================================================================// export LC_ALL='C' sed -i -e '/Patterns/!s/\("[A-Z0-9_]\+[ "e]\)/\L\1/g' SIInstructions.td sed -i -e 's/"EXP/"exp/g' SIInstrInfo.td git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@221350 91177308-0d34-0410-b5e6-96231b3b80d8
2014-11-05 14:50:53 +00:00
; SI: s_load_dwordx2 s{{\[}}[[LO_SREG:[0-9]+]]:{{[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0xd
; SI: s_lshl_b64 s{{\[}}[[LO_SHL:[0-9]+]]:{{[0-9]+\]}}, s{{\[}}[[LO_SREG]]:{{[0-9]+\]}}, 2
; SI: s_add_u32 s[[LO_SREG2:[0-9]+]], s[[LO_SHL]],
AMDGPU/SI: Implement a custom MachineSchedStrategy Summary: GCNSchedStrategy re-uses most of GenericScheduler, it's just uses a different method to compute the excess and critical register pressure limits. It's not enabled by default, to enable it you need to pass -misched=gcn to llc. Shader DB stats: 32464 shaders in 17874 tests Totals: SGPRS: 1542846 -> 1643125 (6.50 %) VGPRS: 1005595 -> 904653 (-10.04 %) Spilled SGPRs: 29929 -> 27745 (-7.30 %) Spilled VGPRs: 334 -> 352 (5.39 %) Scratch VGPRs: 1612 -> 1624 (0.74 %) dwords per thread Code Size: 36688188 -> 37034900 (0.95 %) bytes LDS: 1913 -> 1913 (0.00 %) blocks Max Waves: 254101 -> 265125 (4.34 %) Wait states: 0 -> 0 (0.00 %) Totals from affected shaders: SGPRS: 1338220 -> 1438499 (7.49 %) VGPRS: 886221 -> 785279 (-11.39 %) Spilled SGPRs: 29869 -> 27685 (-7.31 %) Spilled VGPRs: 334 -> 352 (5.39 %) Scratch VGPRs: 1612 -> 1624 (0.74 %) dwords per thread Code Size: 34315716 -> 34662428 (1.01 %) bytes LDS: 1551 -> 1551 (0.00 %) blocks Max Waves: 188127 -> 199151 (5.86 %) Wait states: 0 -> 0 (0.00 %) Reviewers: arsenm, mareko, nhaehnle, MatzeB, atrick Subscribers: arsenm, kzhuravl, llvm-commits Differential Revision: https://reviews.llvm.org/D23688 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@279995 91177308-0d34-0410-b5e6-96231b3b80d8
2016-08-29 19:42:52 +00:00
; SI: v_mov_b32_e32 v[[LO_VREG:[0-9]+]], s[[LO_SREG2]]
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" MATCHES=`grep -v Patterns SIInstructions.td | grep -o '"[A-Z0-9_]\+["e]' | grep -o '[A-Z0-9_]\+' | sort -r` for f in $TEST_FILES; do # Check that there are SI tests: grep -q -e 'verde' -e 'bonaire' -e 'SI' -e 'tahiti' $f if [ $? -eq 0 ]; then for match in $MATCHES; do sed -i -e "s/\([ :]$match\)/\L\1/" $f done # Try to get check lines with partial instruction names sed -i 's/\(;[ ]*SI[A-Z\\-]*: \)\([A-Z_0-9]\+\)/\1\L\2/' $f fi done sed -i -e 's/bb0_1/BB0_1/g' ../../../test/CodeGen/R600/infinite-loop.ll sed -i -e 's/SI-NOT: bfe/SI-NOT: {{[^@]}}bfe/g'../../../test/CodeGen/R600/llvm.AMDGPU.bfe.*32.ll ../../../test/CodeGen/R600/sext-in-reg.ll sed -i -e 's/exp_IEEE/EXP_IEEE/g' ../../../test/CodeGen/R600/llvm.exp2.ll sed -i -e 's/numVgprs/NumVgprs/g' ../../../test/CodeGen/R600/register-count-comments.ll sed -i 's/\(; CHECK[-NOT]*: \)\([A-Z_0-9]\+\)/\1\L\2/' ../../../test/CodeGen/R600/select64.ll ../../../test/CodeGen/R600/sgpr-copy.ll //==================================================================// // Shell script for converting .td files (run this last) //==================================================================// export LC_ALL='C' sed -i -e '/Patterns/!s/\("[A-Z0-9_]\+[ "e]\)/\L\1/g' SIInstructions.td sed -i -e 's/"EXP/"exp/g' SIInstrInfo.td git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@221350 91177308-0d34-0410-b5e6-96231b3b80d8
2014-11-05 14:50:53 +00:00
; SI: s_addc_u32
AMDGPU/SI: Implement a custom MachineSchedStrategy Summary: GCNSchedStrategy re-uses most of GenericScheduler, it's just uses a different method to compute the excess and critical register pressure limits. It's not enabled by default, to enable it you need to pass -misched=gcn to llc. Shader DB stats: 32464 shaders in 17874 tests Totals: SGPRS: 1542846 -> 1643125 (6.50 %) VGPRS: 1005595 -> 904653 (-10.04 %) Spilled SGPRs: 29929 -> 27745 (-7.30 %) Spilled VGPRs: 334 -> 352 (5.39 %) Scratch VGPRs: 1612 -> 1624 (0.74 %) dwords per thread Code Size: 36688188 -> 37034900 (0.95 %) bytes LDS: 1913 -> 1913 (0.00 %) blocks Max Waves: 254101 -> 265125 (4.34 %) Wait states: 0 -> 0 (0.00 %) Totals from affected shaders: SGPRS: 1338220 -> 1438499 (7.49 %) VGPRS: 886221 -> 785279 (-11.39 %) Spilled SGPRs: 29869 -> 27685 (-7.31 %) Spilled VGPRs: 334 -> 352 (5.39 %) Scratch VGPRs: 1612 -> 1624 (0.74 %) dwords per thread Code Size: 34315716 -> 34662428 (1.01 %) bytes LDS: 1551 -> 1551 (0.00 %) blocks Max Waves: 188127 -> 199151 (5.86 %) Wait states: 0 -> 0 (0.00 %) Reviewers: arsenm, mareko, nhaehnle, MatzeB, atrick Subscribers: arsenm, kzhuravl, llvm-commits Differential Revision: https://reviews.llvm.org/D23688 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@279995 91177308-0d34-0410-b5e6-96231b3b80d8
2016-08-29 19:42:52 +00:00
; SI: buffer_store_dword v[[LO_VREG]],
R600/SI: Define a schedule model and enable the generic machine scheduler The schedule model is not complete yet, and could be improved. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@227461 91177308-0d34-0410-b5e6-96231b3b80d8
2015-01-29 16:55:25 +00:00
; SI: v_mov_b32_e32
AMDGPU/SI: Enable the post-ra scheduler Summary: This includes a hazard recognizer implementation to replace some of the hazard handling we had during frame index elimination. Reviewers: arsenm Subscribers: qcolombet, arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D18602 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@268143 91177308-0d34-0410-b5e6-96231b3b80d8
2016-04-30 00:23:06 +00:00
; SI: v_mov_b32_e32
R600: Implement isZExtFree. This allows 64-bit operations that are truncated to be reduced to 32-bit ones. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@204946 91177308-0d34-0410-b5e6-96231b3b80d8
2014-03-27 17:23:31 +00:00
define void @trunc_shl_i64(i64 addrspace(1)* %out2, i32 addrspace(1)* %out, i64 %a) {
R600: Implement isNarrowingProfitable. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@204658 91177308-0d34-0410-b5e6-96231b3b80d8
2014-03-24 19:43:31 +00:00
%aa = add i64 %a, 234 ; Prevent shrinking store.
%b = shl i64 %aa, 2
R600: Fix trunc i64 to i32 on SI git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192375 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-10 18:04:16 +00:00
%result = trunc i64 %b to i32
store i32 %result, i32 addrspace(1)* %out, align 4
R600: Implement isZExtFree. This allows 64-bit operations that are truncated to be reduced to 32-bit ones. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@204946 91177308-0d34-0410-b5e6-96231b3b80d8
2014-03-27 17:23:31 +00:00
store i64 %b, i64 addrspace(1)* %out2, align 8 ; Prevent reducing ops to 32-bits
R600: Fix trunc i64 to i32 on SI git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192375 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-10 18:04:16 +00:00
ret void
}
R600/SI: Add pattern for truncating i32 to i1 Fixes half a dozen piglit tests with radeonsi. Reviewed-by: Tom Stellard <thomas.stellard@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200283 91177308-0d34-0410-b5e6-96231b3b80d8
2014-01-28 03:01:16 +00:00
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218776 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-01 17:15:17 +00:00
; SI-LABEL: {{^}}trunc_i32_to_i1:
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" MATCHES=`grep -v Patterns SIInstructions.td | grep -o '"[A-Z0-9_]\+["e]' | grep -o '[A-Z0-9_]\+' | sort -r` for f in $TEST_FILES; do # Check that there are SI tests: grep -q -e 'verde' -e 'bonaire' -e 'SI' -e 'tahiti' $f if [ $? -eq 0 ]; then for match in $MATCHES; do sed -i -e "s/\([ :]$match\)/\L\1/" $f done # Try to get check lines with partial instruction names sed -i 's/\(;[ ]*SI[A-Z\\-]*: \)\([A-Z_0-9]\+\)/\1\L\2/' $f fi done sed -i -e 's/bb0_1/BB0_1/g' ../../../test/CodeGen/R600/infinite-loop.ll sed -i -e 's/SI-NOT: bfe/SI-NOT: {{[^@]}}bfe/g'../../../test/CodeGen/R600/llvm.AMDGPU.bfe.*32.ll ../../../test/CodeGen/R600/sext-in-reg.ll sed -i -e 's/exp_IEEE/EXP_IEEE/g' ../../../test/CodeGen/R600/llvm.exp2.ll sed -i -e 's/numVgprs/NumVgprs/g' ../../../test/CodeGen/R600/register-count-comments.ll sed -i 's/\(; CHECK[-NOT]*: \)\([A-Z_0-9]\+\)/\1\L\2/' ../../../test/CodeGen/R600/select64.ll ../../../test/CodeGen/R600/sgpr-copy.ll //==================================================================// // Shell script for converting .td files (run this last) //==================================================================// export LC_ALL='C' sed -i -e '/Patterns/!s/\("[A-Z0-9_]\+[ "e]\)/\L\1/g' SIInstructions.td sed -i -e 's/"EXP/"exp/g' SIInstrInfo.td git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@221350 91177308-0d34-0410-b5e6-96231b3b80d8
2014-11-05 14:50:53 +00:00
; SI: v_and_b32_e32 v{{[0-9]+}}, 1, v{{[0-9]+}}
AMDGPU: Use unsigned compare for eq/ne For some reason there are both of these available, except for scalar 64-bit compares which only has u64. I'm not sure why there are both (I'm guessing it's for the one bit inputs we don't use), but for consistency always using the unsigned one. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@282832 91177308-0d34-0410-b5e6-96231b3b80d8
2016-09-30 01:50:20 +00:00
; SI: v_cmp_eq_u32
R600/SI: Prefer selecting more e64 instruction forms. Add some more tests to make sure better operand choices are still made. Leave some cases that seem to have no reason to ever be e64 alone. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@217789 91177308-0d34-0410-b5e6-96231b3b80d8
2014-09-15 17:15:02 +00:00
define void @trunc_i32_to_i1(i32 addrspace(1)* %out, i32 addrspace(1)* %ptr) {
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@230794 91177308-0d34-0410-b5e6-96231b3b80d8
2015-02-27 21:17:42 +00:00
%a = load i32, i32 addrspace(1)* %ptr, align 4
R600/SI: Prefer selecting more e64 instruction forms. Add some more tests to make sure better operand choices are still made. Leave some cases that seem to have no reason to ever be e64 alone. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@217789 91177308-0d34-0410-b5e6-96231b3b80d8
2014-09-15 17:15:02 +00:00
%trunc = trunc i32 %a to i1
%result = select i1 %trunc, i32 1, i32 0
store i32 %result, i32 addrspace(1)* %out, align 4
ret void
}
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218776 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-01 17:15:17 +00:00
; SI-LABEL: {{^}}sgpr_trunc_i32_to_i1:
AMDGPU/SI: use S_AND for i1 trunc git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@251630 91177308-0d34-0410-b5e6-96231b3b80d8
2015-10-29 15:05:03 +00:00
; SI: s_and_b32 s{{[0-9]+}}, 1, s{{[0-9]+}}
AMDGPU: Use unsigned compare for eq/ne For some reason there are both of these available, except for scalar 64-bit compares which only has u64. I'm not sure why there are both (I'm guessing it's for the one bit inputs we don't use), but for consistency always using the unsigned one. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@282832 91177308-0d34-0410-b5e6-96231b3b80d8
2016-09-30 01:50:20 +00:00
; SI: v_cmp_eq_u32
R600/SI: Prefer selecting more e64 instruction forms. Add some more tests to make sure better operand choices are still made. Leave some cases that seem to have no reason to ever be e64 alone. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@217789 91177308-0d34-0410-b5e6-96231b3b80d8
2014-09-15 17:15:02 +00:00
define void @sgpr_trunc_i32_to_i1(i32 addrspace(1)* %out, i32 %a) {
R600/SI: Add pattern for truncating i32 to i1 Fixes half a dozen piglit tests with radeonsi. Reviewed-by: Tom Stellard <thomas.stellard@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200283 91177308-0d34-0410-b5e6-96231b3b80d8
2014-01-28 03:01:16 +00:00
%trunc = trunc i32 %a to i1
%result = select i1 %trunc, i32 1, i32 0
store i32 %result, i32 addrspace(1)* %out, align 4
ret void
}
R600/SI: Fix i64 truncate to i1 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@228273 91177308-0d34-0410-b5e6-96231b3b80d8
2015-02-05 06:05:13 +00:00
; SI-LABEL: {{^}}s_trunc_i64_to_i1:
; SI: s_load_dwordx2 s{{\[}}[[SLO:[0-9]+]]:{{[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0xb
AMDGPU/SI: use S_AND for i1 trunc git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@251630 91177308-0d34-0410-b5e6-96231b3b80d8
2015-10-29 15:05:03 +00:00
; SI: s_and_b32 [[MASKED:s[0-9]+]], 1, s[[SLO]]
AMDGPU: Use unsigned compare for eq/ne For some reason there are both of these available, except for scalar 64-bit compares which only has u64. I'm not sure why there are both (I'm guessing it's for the one bit inputs we don't use), but for consistency always using the unsigned one. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@282832 91177308-0d34-0410-b5e6-96231b3b80d8
2016-09-30 01:50:20 +00:00
; SI: v_cmp_eq_u32_e64 s{{\[}}[[VLO:[0-9]+]]:[[VHI:[0-9]+]]], [[MASKED]], 1{{$}}
AMDGPU/SI: use S_AND for i1 trunc git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@251630 91177308-0d34-0410-b5e6-96231b3b80d8
2015-10-29 15:05:03 +00:00
; SI: v_cndmask_b32_e64 {{v[0-9]+}}, -12, 63, s{{\[}}[[VLO]]:[[VHI]]]
R600/SI: Fix i64 truncate to i1 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@228273 91177308-0d34-0410-b5e6-96231b3b80d8
2015-02-05 06:05:13 +00:00
define void @s_trunc_i64_to_i1(i32 addrspace(1)* %out, i64 %x) {
%trunc = trunc i64 %x to i1
%sel = select i1 %trunc, i32 63, i32 -12
store i32 %sel, i32 addrspace(1)* %out
ret void
}
; SI-LABEL: {{^}}v_trunc_i64_to_i1:
; SI: buffer_load_dwordx2 v{{\[}}[[VLO:[0-9]+]]:{{[0-9]+\]}}
; SI: v_and_b32_e32 [[MASKED:v[0-9]+]], 1, v[[VLO]]
AMDGPU: Use unsigned compare for eq/ne For some reason there are both of these available, except for scalar 64-bit compares which only has u64. I'm not sure why there are both (I'm guessing it's for the one bit inputs we don't use), but for consistency always using the unsigned one. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@282832 91177308-0d34-0410-b5e6-96231b3b80d8
2016-09-30 01:50:20 +00:00
; SI: v_cmp_eq_u32_e32 vcc, 1, [[MASKED]]
R600/SI: Allow commuting compares This enables very common cases to switch to the smaller encoding. All of the standard LLVM canonicalizations of comparisons are the opposite of what we want. Compares with constants are moved to the RHS, but the first operand can be an inline immediate, literal constant, or SGPR using the 32-bit VOPC encoding. There are additional bad canonicalizations that should also be fixed, such as canonicalizing ge x, k to gt x, (k + 1) if this makes k no longer an inline immediate value. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@232988 91177308-0d34-0410-b5e6-96231b3b80d8
2015-03-23 18:45:30 +00:00
; SI: v_cndmask_b32_e64 {{v[0-9]+}}, -12, 63, vcc
R600/SI: Fix i64 truncate to i1 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@228273 91177308-0d34-0410-b5e6-96231b3b80d8
2015-02-05 06:05:13 +00:00
define void @v_trunc_i64_to_i1(i32 addrspace(1)* %out, i64 addrspace(1)* %in) {
%tid = call i32 @llvm.r600.read.tidig.x() nounwind readnone
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction One of several parallel first steps to remove the target type of pointers, replacing them with a single opaque pointer type. This adds an explicit type parameter to the gep instruction so that when the first parameter becomes an opaque pointer type, the type to gep through is still available to the instructions. * This doesn't modify gep operators, only instructions (operators will be handled separately) * Textual IR changes only. Bitcode (including upgrade) and changing the in-memory representation will be in separate changes. * geps of vectors are transformed as: getelementptr <4 x float*> %x, ... ->getelementptr float, <4 x float*> %x, ... Then, once the opaque pointer type is introduced, this will ultimately look like: getelementptr float, <4 x ptr> %x with the unambiguous interpretation that it is a vector of pointers to float. * address spaces remain on the pointer, not the type: getelementptr float addrspace(1)* %x ->getelementptr float, float addrspace(1)* %x Then, eventually: getelementptr float, ptr addrspace(1) %x Importantly, the massive amount of test case churn has been automated by same crappy python code. I had to manually update a few test cases that wouldn't fit the script's model (r228970,r229196,r229197,r229198). The python script just massages stdin and writes the result to stdout, I then wrapped that in a shell script to handle replacing files, then using the usual find+xargs to migrate all the files. update.py: import fileinput import sys import re ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))") normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))") def conv(match, line): if not match: return line line = match.groups()[0] if len(match.groups()[5]) == 0: line += match.groups()[2] line += match.groups()[3] line += ", " line += match.groups()[1] line += "\n" return line for line in sys.stdin: if line.find("getelementptr ") == line.find("getelementptr inbounds"): if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("): line = conv(re.match(ibrep, line), line) elif line.find("getelementptr ") != line.find("getelementptr ("): line = conv(re.match(normrep, line), line) sys.stdout.write(line) apply.sh: for name in "$@" do python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name" rm -f "$name.tmp" done The actual commands: From llvm/src: find test/ -name *.ll | xargs ./apply.sh From llvm/src/tools/clang: find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}" From llvm/src/tools/polly: find test/ -name *.ll | xargs ./apply.sh After that, check-all (with llvm, clang, clang-tools-extra, lld, compiler-rt, and polly all checked out). The extra 'rm' in the apply.sh script is due to a few files in clang's test suite using interesting unicode stuff that my python script was throwing exceptions on. None of those files needed to be migrated, so it seemed sufficient to ignore those cases. Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7636 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@230786 91177308-0d34-0410-b5e6-96231b3b80d8
2015-02-27 19:29:02 +00:00
%gep = getelementptr i64, i64 addrspace(1)* %in, i32 %tid
%out.gep = getelementptr i32, i32 addrspace(1)* %out, i32 %tid
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@230794 91177308-0d34-0410-b5e6-96231b3b80d8
2015-02-27 21:17:42 +00:00
%x = load i64, i64 addrspace(1)* %gep
R600/SI: Fix i64 truncate to i1 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@228273 91177308-0d34-0410-b5e6-96231b3b80d8
2015-02-05 06:05:13 +00:00
%trunc = trunc i64 %x to i1
%sel = select i1 %trunc, i32 63, i32 -12
store i32 %sel, i32 addrspace(1)* %out.gep
ret void
}
Reference in New Issue Copy Permalink