diff options
author | Hal Finkel <hfinkel@anl.gov> | 2013-04-01 17:52:07 +0000 |
---|---|---|
committer | Hal Finkel <hfinkel@anl.gov> | 2013-04-01 17:52:07 +0000 |
commit | 46479197843ecb651adc9417c49bbd1b00acfcb6 (patch) | |
tree | 143df888333c2baabf6cf07c8ef7297b86b5035c /test/CodeGen/PowerPC | |
parent | a1f4290ac94f34173e3561c717390de07dccc646 (diff) | |
download | llvm-46479197843ecb651adc9417c49bbd1b00acfcb6.tar.gz llvm-46479197843ecb651adc9417c49bbd1b00acfcb6.tar.bz2 llvm-46479197843ecb651adc9417c49bbd1b00acfcb6.tar.xz |
Add more PPC floating-point conversion instructions
The P7 and A2 have additional floating-point conversion instructions which
allow a direct two-instruction sequence (plus load/store) to convert from all
combinations (signed/unsigned i32/i64) <--> (float/double) (on previous cores,
only some combinations were directly available).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178480 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/CodeGen/PowerPC')
-rw-r--r-- | test/CodeGen/PowerPC/float-to-int.ll | 92 | ||||
-rw-r--r-- | test/CodeGen/PowerPC/i32-to-float.ll | 41 | ||||
-rw-r--r-- | test/CodeGen/PowerPC/i64-to-float.ll | 52 | ||||
-rw-r--r-- | test/CodeGen/PowerPC/i64_fp_round.ll | 4 | ||||
-rw-r--r-- | test/CodeGen/PowerPC/stfiwx-2.ll | 9 |
5 files changed, 191 insertions, 7 deletions
diff --git a/test/CodeGen/PowerPC/float-to-int.ll b/test/CodeGen/PowerPC/float-to-int.ll new file mode 100644 index 0000000000..ebd0903358 --- /dev/null +++ b/test/CodeGen/PowerPC/float-to-int.ll @@ -0,0 +1,92 @@ +; RUN: llc < %s -mtriple=powerpc64-unknown-linux-gnu -mcpu=a2 | FileCheck %s +target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-f128:128:128-v128:128:128-n32:64" +target triple = "powerpc64-unknown-linux-gnu" + +define i64 @foo(float %a) nounwind { + %x = fptosi float %a to i64 + ret i64 %x + +; CHECK: @foo +; CHECK: fctidz [[REG:[0-9]+]], 1 +; CHECK: stfd [[REG]], +; CHECK: ld 3, +; CHECK: blr +} + +define i64 @foo2(double %a) nounwind { + %x = fptosi double %a to i64 + ret i64 %x + +; CHECK: @foo2 +; CHECK: fctidz [[REG:[0-9]+]], 1 +; CHECK: stfd [[REG]], +; CHECK: ld 3, +; CHECK: blr +} + +define i64 @foo3(float %a) nounwind { + %x = fptoui float %a to i64 + ret i64 %x + +; CHECK: @foo3 +; CHECK: fctiduz [[REG:[0-9]+]], 1 +; CHECK: stfd [[REG]], +; CHECK: ld 3, +; CHECK: blr +} + +define i64 @foo4(double %a) nounwind { + %x = fptoui double %a to i64 + ret i64 %x + +; CHECK: @foo4 +; CHECK: fctiduz [[REG:[0-9]+]], 1 +; CHECK: stfd [[REG]], +; CHECK: ld 3, +; CHECK: blr +} + +define i32 @goo(float %a) nounwind { + %x = fptosi float %a to i32 + ret i32 %x + +; CHECK: @goo +; CHECK: fctiwz [[REG:[0-9]+]], 1 +; CHECK: stfiwx [[REG]], +; CHECK: lwz 3, +; CHECK: blr +} + +define i32 @goo2(double %a) nounwind { + %x = fptosi double %a to i32 + ret i32 %x + +; CHECK: @goo2 +; CHECK: fctiwz [[REG:[0-9]+]], 1 +; CHECK: stfiwx [[REG]], +; CHECK: lwz 3, +; CHECK: blr +} + +define i32 @goo3(float %a) nounwind { + %x = fptoui float %a to i32 + ret i32 %x + +; CHECK: @goo3 +; CHECK: fctiwuz [[REG:[0-9]+]], 1 +; CHECK: stfiwx [[REG]], +; CHECK: lwz 3, +; CHECK: blr +} + +define i32 @goo4(double %a) nounwind { + %x = fptoui double %a to i32 + ret i32 %x + +; CHECK: @goo4 +; CHECK: fctiwuz [[REG:[0-9]+]], 1 +; CHECK: stfiwx [[REG]], +; CHECK: lwz 3, +; CHECK: blr +} + diff --git a/test/CodeGen/PowerPC/i32-to-float.ll b/test/CodeGen/PowerPC/i32-to-float.ll index bed940c5de..2707d0352d 100644 --- a/test/CodeGen/PowerPC/i32-to-float.ll +++ b/test/CodeGen/PowerPC/i32-to-float.ll @@ -1,4 +1,5 @@ ; RUN: llc < %s -mtriple=powerpc64-unknown-linux-gnu -mcpu=g5 | FileCheck %s +; RUN: llc < %s -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr6 | FileCheck -check-prefix=CHECK-PWR6 %s ; RUN: llc < %s -mtriple=powerpc64-unknown-linux-gnu -mcpu=a2 | FileCheck -check-prefix=CHECK-A2 %s target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-f128:128:128-v128:128:128-n32:64" target triple = "powerpc64-unknown-linux-gnu" @@ -16,11 +17,17 @@ entry: ; CHECK: frsp 1, [[REG3]] ; CHECK: blr +; CHECK-PWR6: @foo +; CHECK-PWR6: stw 3, +; CHECK-PWR6: lfiwax [[REG:[0-9]+]], +; CHECK-PWR6: fcfid [[REG2:[0-9]+]], [[REG]] +; CHECK-PWR6: frsp 1, [[REG2]] +; CHECK-PWR6: blr + ; CHECK-A2: @foo ; CHECK-A2: stw 3, ; CHECK-A2: lfiwax [[REG:[0-9]+]], -; CHECK-A2: fcfid [[REG2:[0-9]+]], [[REG]] -; CHECK-A2: frsp 1, [[REG2]] +; CHECK-A2: fcfids 1, [[REG]] ; CHECK-A2: blr } @@ -36,6 +43,12 @@ entry: ; CHECK: fcfid 1, [[REG2]] ; CHECK: blr +; CHECK-PWR6: @goo +; CHECK-PWR6: stw 3, +; CHECK-PWR6: lfiwax [[REG:[0-9]+]], +; CHECK-PWR6: fcfid 1, [[REG]] +; CHECK-PWR6: blr + ; CHECK-A2: @goo ; CHECK-A2: stw 3, ; CHECK-A2: lfiwax [[REG:[0-9]+]], @@ -43,3 +56,27 @@ entry: ; CHECK-A2: blr } +define float @foou(i32 %a) nounwind { +entry: + %x = uitofp i32 %a to float + ret float %x + +; CHECK-A2: @foou +; CHECK-A2: stw 3, +; CHECK-A2: lfiwzx [[REG:[0-9]+]], +; CHECK-A2: fcfidus 1, [[REG]] +; CHECK-A2: blr +} + +define double @goou(i32 %a) nounwind { +entry: + %x = uitofp i32 %a to double + ret double %x + +; CHECK-A2: @goou +; CHECK-A2: stw 3, +; CHECK-A2: lfiwzx [[REG:[0-9]+]], +; CHECK-A2: fcfidu 1, [[REG]] +; CHECK-A2: blr +} + diff --git a/test/CodeGen/PowerPC/i64-to-float.ll b/test/CodeGen/PowerPC/i64-to-float.ll new file mode 100644 index 0000000000..b81d109e7f --- /dev/null +++ b/test/CodeGen/PowerPC/i64-to-float.ll @@ -0,0 +1,52 @@ +; RUN: llc < %s -mtriple=powerpc64-unknown-linux-gnu -mcpu=a2 | FileCheck %s +target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-f128:128:128-v128:128:128-n32:64" +target triple = "powerpc64-unknown-linux-gnu" + +define float @foo(i64 %a) nounwind { +entry: + %x = sitofp i64 %a to float + ret float %x + +; CHECK: @foo +; CHECK: std 3, +; CHECK: lfd [[REG:[0-9]+]], +; CHECK: fcfids 1, [[REG]] +; CHECK: blr +} + +define double @goo(i64 %a) nounwind { +entry: + %x = sitofp i64 %a to double + ret double %x + +; CHECK: @goo +; CHECK: std 3, +; CHECK: lfd [[REG:[0-9]+]], +; CHECK: fcfid 1, [[REG]] +; CHECK: blr +} + +define float @foou(i64 %a) nounwind { +entry: + %x = uitofp i64 %a to float + ret float %x + +; CHECK: @foou +; CHECK: std 3, +; CHECK: lfd [[REG:[0-9]+]], +; CHECK: fcfidus 1, [[REG]] +; CHECK: blr +} + +define double @goou(i64 %a) nounwind { +entry: + %x = uitofp i64 %a to double + ret double %x + +; CHECK: @goou +; CHECK: std 3, +; CHECK: lfd [[REG:[0-9]+]], +; CHECK: fcfidu 1, [[REG]] +; CHECK: blr +} + diff --git a/test/CodeGen/PowerPC/i64_fp_round.ll b/test/CodeGen/PowerPC/i64_fp_round.ll index 5ae1be8953..d2a3239ab8 100644 --- a/test/CodeGen/PowerPC/i64_fp_round.ll +++ b/test/CodeGen/PowerPC/i64_fp_round.ll @@ -1,4 +1,4 @@ -; RUN: llc -mcpu=pwr7 < %s | FileCheck %s +; RUN: llc -mcpu=pwr7 -mattr=-fpcvt < %s | FileCheck %s target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v128:128:128-n32:64" target triple = "powerpc64-unknown-linux-gnu" @@ -22,6 +22,6 @@ entry: ; Also check that with -enable-unsafe-fp-math we do not get that extra ; code sequence. Simply verify that there is no "isel" present. -; RUN: llc -mcpu=pwr7 -enable-unsafe-fp-math < %s | FileCheck %s -check-prefix=UNSAFE +; RUN: llc -mcpu=pwr7 -mattr=-fpcvt -enable-unsafe-fp-math < %s | FileCheck %s -check-prefix=UNSAFE ; CHECK-UNSAFE-NOT: isel diff --git a/test/CodeGen/PowerPC/stfiwx-2.ll b/test/CodeGen/PowerPC/stfiwx-2.ll index c49b25cc23..345f1c93e8 100644 --- a/test/CodeGen/PowerPC/stfiwx-2.ll +++ b/test/CodeGen/PowerPC/stfiwx-2.ll @@ -1,11 +1,14 @@ -; This cannot be a stfiwx -; RUN: llc < %s -march=ppc32 -mcpu=g5 | grep stb -; RUN: llc < %s -march=ppc32 -mcpu=g5 | not grep stfiwx +; RUN: llc < %s -march=ppc32 -mcpu=g5 | FileCheck %s define void @test(float %F, i8* %P) { %I = fptosi float %F to i32 %X = trunc i32 %I to i8 store i8 %X, i8* %P ret void +; CHECK: fctiwz 0, 1 +; CHECK: stfiwx 0, 0, 4 +; CHECK: lwz 4, 12(1) +; CHECK: stb 4, 0(3) +; CHECK: blr } |